{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ARJWK2WFIW5VDFHF3X5VGPWXPM","short_pith_number":"pith:ARJWK2WF","schema_version":"1.0","canonical_sha256":"0453656ac545bb5194e5ddfb533ed77b0429537a4bf9d1fb6c376fc68361e4f8","source":{"kind":"arxiv","id":"2203.08212","version":1},"attestation_state":"computed","paper":{"title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aakriti, Alexandre V. Evfimievski, Ganesh Ramakrishnan, Guttu Sai Abhishek, Krishnateja Killamsetty, Lucian Popa, Rishabh Iyer","submitted_at":"2022-03-15T19:25:01Z","abstract_excerpt":"Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter configuration, even with state-of-the-art (SOTA) hyper-parameter optimization (HPO) algorithms, can be time-consuming, requiring multiple training runs over the entire dataset for different possible sets of hyper-parameters. Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.08212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-15T19:25:01Z","cross_cats_sorted":[],"title_canon_sha256":"b9e49653ba3d57cc4ef15008a57a3d7fdb65cf4d7622811337323e98ea30fc70","abstract_canon_sha256":"e182fdb4ff2ea072400753da5112328842fff84ed1f2c451b0d7c1ba63c133f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:41.053030Z","signature_b64":"H8brH7vm34Gungpyxe07ud8GT1hKp86EeY+PfXwaFFIbR4+lXZSBtPaUcPQtoqtyhUBOKSRpYFsurTyziGJiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0453656ac545bb5194e5ddfb533ed77b0429537a4bf9d1fb6c376fc68361e4f8","last_reissued_at":"2026-07-05T04:05:41.052515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:41.052515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aakriti, Alexandre V. Evfimievski, Ganesh Ramakrishnan, Guttu Sai Abhishek, Krishnateja Killamsetty, Lucian Popa, Rishabh Iyer","submitted_at":"2022-03-15T19:25:01Z","abstract_excerpt":"Deep neural networks have seen great success in recent years; however, training a deep model is often challenging as its performance heavily depends on the hyper-parameters used. In addition, finding the optimal hyper-parameter configuration, even with state-of-the-art (SOTA) hyper-parameter optimization (HPO) algorithms, can be time-consuming, requiring multiple training runs over the entire dataset for different possible sets of hyper-parameters. Our central insight is that using an informative subset of the dataset for model training runs involved in hyper-parameter optimization, allows us "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08212","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.08212/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.08212","created_at":"2026-07-05T04:05:41.052587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08212v1","created_at":"2026-07-05T04:05:41.052587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08212","created_at":"2026-07-05T04:05:41.052587+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARJWK2WFIW5V","created_at":"2026-07-05T04:05:41.052587+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARJWK2WFIW5VDFHF","created_at":"2026-07-05T04:05:41.052587+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARJWK2WF","created_at":"2026-07-05T04:05:41.052587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21003","citing_title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM","json":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM.json","graph_json":"https://pith.science/api/pith-number/ARJWK2WFIW5VDFHF3X5VGPWXPM/graph.json","events_json":"https://pith.science/api/pith-number/ARJWK2WFIW5VDFHF3X5VGPWXPM/events.json","paper":"https://pith.science/paper/ARJWK2WF"},"agent_actions":{"view_html":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM","download_json":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM.json","view_paper":"https://pith.science/paper/ARJWK2WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08212&json=true","fetch_graph":"https://pith.science/api/pith-number/ARJWK2WFIW5VDFHF3X5VGPWXPM/graph.json","fetch_events":"https://pith.science/api/pith-number/ARJWK2WFIW5VDFHF3X5VGPWXPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM/action/storage_attestation","attest_author":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM/action/author_attestation","sign_citation":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM/action/citation_signature","submit_replication":"https://pith.science/pith/ARJWK2WFIW5VDFHF3X5VGPWXPM/action/replication_record"}},"created_at":"2026-07-05T04:05:41.052587+00:00","updated_at":"2026-07-05T04:05:41.052587+00:00"}